Missing-data imputation using wearable sensors in heart rate variability

• Autorzy: Tlija A. , Węgrzyn-Wolska K. , Istrate D.

Identyfikatory

DOI

10.24425/bpasts.2020.133118

• Języki publikacji: EN

Abstrakty

EN

The objective of this work is to set up a methodology that considers missing data from a connected heartbeat sensor in order to propose a good replacement methodology in the context of heart rate variability (HRV) computation. The framework is a research project, which aims to build a system that can measure stress and other factors influencing the onset and development of heart disease. The research encompasses studying existing methods, and improving them by use of experimental data from case study that describe the participant’s everyday life. We conduct a study to modelize stress from the HRV signal, which is extracted from a heart rate monitor belt connected to a smart watch. This paper describes data recording procedure and data imputation methodology. Missing data is a topic that has been discussed by several authors. The manuscript explains why we choose spline interpolation for data values imputation. We implement a random suppression data procedure and simulate removed data. After that, we implement several algorithms and choose the best one for our case study based on the mean square error.

Słowa kluczowe

EN

data imputation; spline interpolation; linear interpolation; HRV; IoT

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2020
• Tom: Vol. 68, nr 2
• Strony: 255--261
• Opis fizyczny: Bibliogr. 28 poz., rys., tab.

Twórcy

autor

Tlija A.

• BMBI UMR 7338, UTC-Sorbonne Universités, Compiègne, France

autor

Węgrzyn-Wolska K.

• AlliansTIC Research Laboratory, EFREI Paris, 30-32 avenue de la République, 94800 Villejuif, France
• Centre de Recherche en Informatique, MINES ParisTech, PSL University, 35 rue St Honore, 77300 Fontainebleau, France

autor

Istrate D.

• BMBI UMR 7338, UTC-Sorbonne Universités, Compiègne, France

Bibliografia

• [1]D. Miorandi, S. Sicari, F. De Pellegrini, and I. Chlamtac, “Internet of things: vision, applications and research challenges,” Ad Hoc Networks 10(7), 1497–1516 (2012).
• [2]C. Li, X. Hu, and L. Zhang, “The IoT-based heart disease monitoring system for pervasive healthcare service,” Procedia Comput. Sci. 112, 2328–2334 (2017).
• [3]I. Montaigne, “Big data and connected object that make France champion” Montaigne’s Institut Report, March 2016, p. 200. [in French].
• [4]Y. Hata, S. Kobashi, and H. Nakajima, “Human health care system of systems,” IEEE Syst. J. 3(2), 231–238, (2009).
• [5]M. Poelman et al., “Relations between the residential fast-food environment and the individual risk of cardiovascular diseases in the Netherlands: a nationwide follow-up study,” Eur. J. Prev. Cardiol., 25(13), 1397–1405 (2018).
• [6]H. Amroun, M.H.H. Temkit, and M. Ammi, “In – Depth Learning of Raw Human Activity Data,” Internet of Things, 1, 1–7 (2017). doi: 10.21494/ISTE.OP.2017.0150 [in French].
• [7]C. Zhu and W. Sheng, “Multi-sensor fusion for daily human activity recognition in robot-assisted living”, in Proceedings of the 4th ACM/IEEE international conference on Human robot interaction, 2009, pp. 303–304.
• [8]L. Bao and S.S. Intille, “Activity recognition from user-annotated acceleration data”, in International conference on pervasive computing pp. 1‒17, Springer, Berlin, Heidelberg , 2004.
• [9]A.J. Brush, A.K. Karlson, J. Scott, R. Sarin, A. Jacobs, B. Bond, O. Murillo, G. Hunt, M. Sinclair, K. Hammil, et al., “User experiences with activity-based navigation on mobile devices”, in Proceedings of the 12th International Conference on Human computer interaction with mobile devices and services, 2010, pp. 73–82.
• [10]M. Kołodziej, P. Tarnowski, A. Majkowski, and R.J. Rak, “Electrodermal activity measurements for detection of emotional arousal”, Bull. Pol. Ac.: Tech. 67(4), 813‒826 (2019).
• [11]D. Huysmans et al., “Unsupervised learning for mental stress detection – exploration of self-organizing maps,” in Proc. 11th Int. Jt. Conf. Biomed. Eng. Syst. Technol., 2018, pp. 26–35.
• [12]M. Buckert, J. Oechssler, and C. Schwieren, “Imitation under stress,” J. Econ. Behav. Organ. 139, 252–266 (2017).
• [13]A. Tlija, D. Istrate, A. Bennani, N. Hoai Huong, S. Gattoufi, and K. Wegrzyn-Wolska, “Monitoring chronic disease at home using connected devices,” 2018 13th Annual Conference on System of Systems Engineering (SoSE), Paris, 2018, pp. 400‒407.
• [14]A. Tlija, D. Istrate, S. Gattoufi, and A. Bennani, “Stress recognition using connected devices: experimentation feedback”, Study Days on TeleHealth, Sorbonne Universities, May 2019, Paris, France (to be published).
• [15]H.G. Kim, E.J. Cheon, D.S. Bai, Y.H. Lee, and B.H. Koo, “Stress and heart rate variability: A meta-analysis and review of the literature,” Psychiatry Investig. 15(3), 235–245 (2018).
• [16]W. von Rosenberg, T. Chanwimalueang, T. Adjei, U. Jaffer, V. Goverdovsky, and D. P. Mandic, “Resolving ambiguities in the LF/HF ratio: LF-HF scatter plots for the categorization of mental and physical stress from HRV,” Front. Physiol. 8, 1–12 (2017).
• [17]F. Shaffer and J.P. Ginsberg, “An overview of heart rate variability metrics and norms”, Front. Public Health 5, 258 (2017).
• [18]M.G. Cicignani, A. Berchtold, “Imputation of Missing Data: Comparison of Different Approaches”, 42th Statistic Days, (inria-00494698), 2010 [in French].
• [19]D.J. Stekhoven and P. Bühlmann, “MissForest – nonparametric missing value imputation for mixed-type data”, Bioinformatics Advance Access, 28(1), 112‒118 (2012).
• [20]J. Honaker, G. King, and M. Blackwell, “Amelia II: A Program for Missing Data,” Journal of Statistical Software, 45(7), 1–47, (2011).
• [21]Hastie et al., “Imputing Missing data for gene expression arrays,” Rap. tech., Division of Biostatistics, Stanford University, 1999.
• [22]R.J.A. Little, D.B. Rubin, Statistical analysis with missing data, Wiley series in probability and statistics, 1987.
• [23]P. Maziewski, “Wow defect reduction based on interpolation techniques”, Bull. Pol. Ac.: Tech. 54 (4), 469–477 (2006).
• [24] W.S. Cleveland and S.J. Devlin, “Locally-Weighted Regression: An approach to regression aalysis by local fitting”, J. Am. Stat. Assoc., 83(403), 596–610 (1988).
• [25] A.J. Feelders, “Handling missing data in trees: Surrogate splits or statistical imputation?,” in Principles of Data Mining and Knowledge Discovery, pp. 329–334 eds. J.M. Zytkow and J. Rauch, Germany: Springer Verlag, 1999.
• [26] C. Preda, G. Saporta, and M. Hedi Ben Hadj Mbarek, “The NI-PALS algorithm for missing functional data”, Romanian Journal of Pure and Applied Mathematics, 55(4), 315–326 (2010).
• [27] K. Lewenstein, M. Jamroży, and T. Leyko, “The use of recurrence plots and beat recordings in chronic heart failure detection”, Bull. Pol. Ac.: Tech. 64(2), 339‒345 (2016)
• [28] A. Gelman, J. Hill, “Data analysis using regression and multi-level/-hierarchical models”, chap. 25, pp. 529–563, Cambridge University Press, 2007.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).